MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback
cs.AI, cs.CL, cs.LG
Submitted: 2026-06-11
Updated: 2026-09-19
Comments: Accepted by EMNLP 2026 Main Conference
Code: https://github.com/Zehong-Wang/MDForge
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MDCrow: Automating Molecular Dynamics Workflows with Large Language Models
- Constitutional AI: Harmlessness from AI Feedback
- Automating MD simulations for Proteins using Large language Models: NAMD-Agent
- Toward Autonomous Long-Horizon Engineering for ML Research
- Training Verifiers to Solve Math Word Problems
- ToPolyAgent: AI Agents for Coarse-Grained Topological Polymer Simulations
- Process Reward Models That Think
- DynaMate: An Autonomous Agent for Protein-Ligand Molecular Dynamics Simulations
- MDAgent: A Multi-Agent Framework for End-to-End Molecular Dynamics Research
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Improve Mathematical Reasoning in Language Models by Automated Process Supervision
- Language Models Can Learn from Verbal Feedback Without Scalar Rewards
- Policy4OOD: A Knowledge-Guided World Model for Policy Intervention Simulation against the Opioid Overdose Crisis
- Proximal Policy Optimization Algorithms
- CRISPR-GPT for Agentic Automation of Gene-editing Experiments
- MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics
- Molecular Representations in Implicit Functional Space via Hyper-Networks
- Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents
- Solving math word problems with process- and outcome-based feedback
- EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection